Atlas Discovery
AI-native pharma company
About Atlas Discovery
AI-native pharma company
Public traction evidence
Each signal links to the public source used for attribution.
- X
Nine out of ten drugs fail in clinical trials. The reason isn't a shortage of data. It's that none of it connects. We started Atlas Disc...
Nine out of ten drugs fail in clinical trials. The reason isn't a shortage of data. It's that none of it connects. We started Atlas Discovery to fix that with foundation models of patient drug response. We're backed by @ycombinator, @pearvc, and more.
- X
Nine out of ten drugs fail in clinical trials because we can’t predict how a patient will respond.
Nine out of ten drugs fail in clinical trials because we can’t predict how a patient will respond. We backtested our foundation model of patient biology on multiple clinical trials in Cancer and Autoimmune diseases and successfully separated responders vs non-responders 70-90% of
- LinkedIn
Founder says he started Atlas Discovery. Post says Atlas Discovery raised funding from Y Combinator.
Founder says he started Atlas Discovery. Post says Atlas Discovery raised funding from Y Combinator.
- X
Today we're excited to announce our partnership with Alliance to Cure.
Today we're excited to announce our partnership with Alliance to Cure. Our biomedical research agents found a novel drug repurposing candidate for Cerebral Cavernous Malformation and the foundation is now running preclinical tests on it!
- X
Humanity’s greatest gains from AI will emerge from healthcare.
Humanity’s greatest gains from AI will emerge from healthcare. Today we’re sharing ClinicBench go evaluate frontier agents’ ability to reason over a patient’s medical history and recommend clinical actions. This is a product of our RL environment for clinical decision agents.
- X
Today, we're excited to share our work on agents for drug repurposing.
Today, we're excited to share our work on agents for drug repurposing. In 2019, a diabetes drug (dapagliflozin) turned out to keep heart failure patients alive, and our biomedical research agents recovered it from first principles.
- X
We’re building foundation models that predict patient response in clinical trials. Excited for the future at @atlasdiscovery0 with @ShaamilKarim1 and @Cgensbigler ! Quote Atlas Discovery @atlasdiscovery0 · Jun 23 Nine out of ten drugs fail in clinical trials. The reason isn't a shortage of data. It's that none of it connects. We started Atlas Discovery to fix that with foundation models of patient drug response. We're backed by @ycombinator, @pearvc, and more.
We’re building foundation models that predict patient response in clinical trials. Excited for the future at @atlasdiscovery0 with @ShaamilKarim1 and @Cgensbigler ! Quote Atlas Discovery @atlasdiscovery0 · Jun 23 Nine out of ten drugs fail in clinical trials. The reason isn't a...
- LinkedIn
Nine out of ten drugs fail in clinical trials. Most failures happen because nothing in the lab reliably predicts how a person will respond, and the data that could close that gap sits in silos that rarely connect a patient's biology to whether the drug worked. At Atlas Discovery, we're building foundation models of patient drug response. We learn the structure of human biology once, across millions of pre-clinical and clinical samples, so a single trial only has to learn the last step: who responds and who doesn't. We've tested this across a number of clinical studies and seen strong results. From a single biopsy taken before treatment, our model predicts which ulcerative colitis patients would respond to ustekinumab at 0.76 AUROC. Applied to the UNIFI phase 3 trial, that accuracy would have reached the same statistical power with 458 fewer patients, 182 instead of 640. The trial has alw
Nine out of ten drugs fail in clinical trials. Most failures happen because nothing in the lab reliably predicts how a person will respond, and the data that could close that gap sits in silos that rarely connect a patient's biology to whether the drug worked. At Atlas...